Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and non-open-world, so safety is covered. The description adds behavior the annotations cannot: the exact return shape ({'plans': [...]}), the fields each row carries, and the non-obvious fact that monthly and yearly Premium are separate rows keyed by billing_interval.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action, followed by a compact return description; no filler sentences. The 'Returns:' block is slightly bulky relative to a no-param list tool, but every line conveys new information about the payload.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no input parameters and no output schema, the description is the sole source of payload information, and it supplies both the top-level envelope and the per-plan field set. Nothing an agent needs to call and interpret this tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Zero parameters, so there is nothing for the description to disambiguate; the documented return fields (id, name, plan_type, price, currency, billing_interval) are value-add rather than parameter compensation. Baseline 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List all active subscription plans') and further pins down scope by naming the concrete plan rows (Free, Premium monthly/yearly). It distinguishes itself from neighbors like get_subscription_status and list_payment_history because it is the catalog of available plans rather than the user's own billing state.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the framing question 'what do I get if I upgrade?', which tells the agent this is a pre-purchase comparison tool. However, no alternative is named (e.g., get_subscription_status for current plan, start_checkout for upgrading), so the agent must infer routing from sibling names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.